Histogram Equalization-Based Features for Speech, Music and Song Discrimination Articles uri icon

publication date

  • July 2010

start page

  • 659

end page

  • 662

issue

  • 7

volume

  • 17

International Standard Serial Number (ISSN)

  • 1070-9908

Electronic International Standard Serial Number (EISSN)

  • 1558-2361

abstract

  • In this letter, we present a new class of segment-based features for speech, music and song discrimination. These features, called PHEQ (Polynomial-Fit Histogram Equalization), are derived from the nonlinear
    relationship between the short-term feature distributions computed at
    segment level and a reference distribution. Results show that PHEQ
    characteristics outperform short-term features such as Mel Frequency
    Cepstrum Coefficients (MFCC) and conventional segment-based ones such as
    MFCC mean and variance. Furthermore, the combination of short-term and
    PHEQ features significantly improves the performance of the whole
    system.

keywords

  • speech/music/song discrimination; audio classification; heq-based features; acoustic features; parameterization